mgiovani/ai-arsenal / skills/docs-diagram
docs-diagram
VerifiedGenerate a Mermaid diagram (ER, architecture, deployment, or security) by reading the actual codebase and writing it to docs/. Use for requests like "draw an ER diagram of these tables", "show me the architecture", "diagram the deployment setup", "visualize the security data flow", or "generate a system diagram". Not for scaffolding a new docs directory structure (use docs-init), syncing existing prose docs with code changes (use docs-update), or recording a design decision's rationale (use docs-adr), this skill only produces diagrams generated from code.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.6 KB |
| assets/templates/architecture.md | markdown | 745 B |
| assets/templates/data-model.md | markdown | 873 B |
| assets/templates/deployment.md | markdown | 829 B |
| assets/templates/security.md | markdown | 705 B |
| evals/evals.json | config | 3.1 KB |
| evals/trigger-eval.json | config | 1.8 KB |
| references/detection-patterns.md | markdown | 1.7 KB |
| references/mermaid-patterns.md | markdown | 3.1 KB |
references/mermaid-patterns.md
View on GitHub# Mermaid Patterns
Mermaid syntax reference for each supported diagram type.
## Contents
- [ER Diagram (`er`)](#er-diagram-er)
- [Architecture Diagram (`arch`)](#architecture-diagram-arch)
- [Deployment Diagram (`deployment`)](#deployment-diagram-deployment)
- [Security Diagram (`security`)](#security-diagram-security)
- [Example Output](#example-output)
## ER Diagram (`er`)
Entity-Relationship diagram from database models.
Detects: Tables and entities, columns with data types, primary keys, foreign keys, relationships, constraints.
```mermaid
erDiagram
USER ||--o| PROFILE : "has"
USER {
uuid id PK
string email UK
string password_hash
}
PROFILE {
uuid id PK
uuid user_id FK
string bio
}
```
### Supported ORMs and what to extract
Python ORMs: SQLAlchemy, Django, Tortoise, SQLModel, Peewee
JS/TS ORMs: Prisma, TypeORM, Sequelize, Mongoose
Other: GORM (Go), ActiveRecord (Ruby)
Extract, per model: tables/entities, columns with types, relationships (one-to-one, one-to-many, many-to-many), and constraints (PK, FK, unique).
### For ER Diagrams Specifically
```
Agent 1 - Find Models:
- prompt: "Find all ORM model/entity files. Extract table names and column definitions."
- subagent_type: "Explore"
Agent 2 - Find Relationships:
- prompt: "In the model files found, identify all foreign keys and relationship decorators. Map actual relationships."
- subagent_type: "Explore"
Only include entities and relationships that both agents confirm exist.
```
## Architecture Diagram (`arch`)
System architecture and component relationships.
Detects: Services and modules, API endpoints, databases, caches, message queues, external services.
```mermaid
graph TB
Client[Web Client]
API[API Server]
DB[(Database)]
Cache[(Redis)]
Client --> API
API --> DB
API --> Cache
```
## Deployment Diagram (`deployment`)
Deployment infrastructure and CI/CD.
Detects: Docker containers, Kubernetes resources, cloud services, CI/CD pipeline stages, environment configurations.
```mermaid
graph LR
Dev[Development]
CI[CI Pipeline]
Stage[Staging]
Prod[Production]
Dev --> CI
CI --> Stage
Stage --> Prod
```
## Security Diagram (`security`)
Security architecture and data flow.
Detects: Authentication flows, authorization boundaries, encryption points, security controls, trust boundaries.
```mermaid
graph TB
User[User]
Auth[Auth Service]
API[Protected API]
DB[(Encrypted DB)]
User -->|JWT| Auth
Auth -->|Validated| API
API -->|TLS| DB
```
## Example Output
```
ER Diagram Generated
Detected: 5 entities, 12 relationships
File: docs/data-model.md
Entities Found:
User (SQLAlchemy model)
Profile (SQLAlchemy model)
Role (SQLAlchemy model)
Permission (SQLAlchemy model)
UserRole (junction table)
Relationships:
User -> Profile (one-to-one)
User -> UserRole (one-to-many)
Role -> UserRole (one-to-many)
Role -> Permission (many-to-many)
Next Steps:
1. Review generated ER diagram
2. Add entity descriptions if needed
3. Update when schema changes
4. Reference in architecture docs
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |